Add new folder for Duy Pham work

Author: dpham2123

Use_Cases/Weather-Aware Routing/Duy Pham/.ipynb_checkpoints/Data_Exploration_Analysis-checkpoint.ipynb

@@ -0,0 +1,45 @@
+
+# EV, Traffic & Weather Analysis
+
+This repository contains data and notebooks for exploring the relationship between traffic conditions, EV charging station data, and weather conditipons and a predictive model of the traffic volume. 
+## Project components
+
+### Datasets
+
+1. **`Weather data.csv`**  
+   Contains daily weather observations for a single station (Melbourne Airport) from 2022 to 2023. Important columns:
+   - `DATE` – observation date  
+   - `PRCP` – daily precipitation (mm)  
+   - `TAVG` – average temperature (°C)  
+   - `TMAX` – maximum temperature (°C)  
+   - `TMIN` – minimum temperature (°C)  
+
+2. **`Traffic data.csv`**  
+   Contains road segments with traffic counts, direction, year, and geometry. Important columns:
+   - `OBJECTID` – unique ID per segment  
+   - `Label` – includes traffic count information (e.g. `450(92)`)  
+   - `Direction` – direction of travel (e.g. `both`)  
+   - `SHAPE_Length` – segment length in map units  
+   - `Year` – year of the traffic count  
+   - `geometry` – `LINESTRING` geometry in WKT format  
+
+3. **`EV stations data.csv`**  
+   Contains EV charging stations information. Important columns:
+   - `OBJECTID` – unique ID per station  
+   - `Type` – type of stall or meter  
+   - `RatePerHour` – hourly parking/charging rate  
+   - `MaxTime` – maximum allowed parking time   
+
+### Notebooks
+
+1. **`Data_Exploration_Analysis.ipynb`**  
+   Jupyter notebook used for initial data exploration and cleaning of the three datasets (traffic, EV stations, and weather). Includes:
+   - Loading the CSV files  
+   - Inspecting basic statistics and distributions  
+   - Visualising temporal and spatial patterns  
+
+2. **`T3-2025.ipynb`**  
+   Main modelling notebook. This notebook:
+   - Engineers features from the raw datasets  
+   - Builds a combined modelling table  
+   - Trains and evaluates a regression model to predict traffic volume